All Commands
Primary workflow
| Command | What it does | When to use |
|---|---|---|
/q-reason | Start structured reasoning — agent auto-selects depth | Non-trivial engineering problem |
/q-note | Record a micro-decision with rationale | Quick tech choice worth remembering |
Full decision cycle
Use these to drive each step manually (or let /q-reason orchestrate):
| Command | What it does | Creates |
|---|---|---|
/q-frame | Frame the problem — signal, constraints, acceptance | ProblemCard |
/q-char | Define comparison dimensions with roles | Characterization (on ProblemCard) |
/q-explore | Generate genuinely distinct variants | SolutionPortfolio |
/q-compare | Fair comparison on the Pareto front | Comparison (on SolutionPortfolio) |
/q-decide | Record decision as contract with invariants | DecisionRecord |
Lifecycle management
| Command | What it does |
|---|---|
/q-refresh | Manage artifact lifecycle — scan stale, waive, reopen, supersede, deprecate, reconcile |
Terminal dashboard
Not a slash command — a CLI command you run directly in your terminal:
quint-code board Interactive TUI with four tabs: Overview (health, activity, depth distribution, coverage), Problems (backlog with drill-in), Decisions (R_eff, drift, glamour markdown detail view), Modules (coverage tree). Live refresh every 3 seconds — run it in a side terminal and it stays current as you work with the agent in another.
Use quint-code board --check for CI/hooks — exits with code 1 if critical issues
exist (R_eff < 0.3, decisions expired > 30 days).
Query & dashboard (MCP)
| Command | What it does |
|---|---|
/q-status | Dashboard via agent — Shipped/Pending decisions, problems, module coverage |
/q-search | Full-text search across all artifacts |
/q-problems | List active problems with readiness signals |
/q-onboard | Discover existing project knowledge and build initial map |
Recommended protocol
/q-frame → /q-char → /q-explore → /q-compare → /q-decide
what's what genuinely fair engineering
broken? matters? different comparison contract
options
You can enter at any step, but the protocol works best in order. /q-char before
/q-explore prevents bias (criteria defined before options). /q-compare
before /q-decide ensures fair evaluation.
Next
- Key concepts — R_eff, CL, WLNK, evidence decay
- FAQ — common questions